{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:26:59Z","timestamp":1783099619425,"version":"3.54.6"},"reference-count":107,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T00:00:00Z","timestamp":1716336000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T00:00:00Z","timestamp":1716336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Key-Area Research and Development Program of Guangdong Province","award":["No.2021B0101200001"],"award-info":[{"award-number":["No.2021B0101200001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876140"],"award-info":[{"award-number":["61876140"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176198"],"award-info":[{"award-number":["62176198"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2065"],"award-info":[{"award-number":["U20B2065"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2048"],"award-info":[{"award-number":["U21B2048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Projects of Zhejiang Lab","award":["No.2019KD0AD01\/010"],"award-info":[{"award-number":["No.2019KD0AD01\/010"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s11263-024-02112-9","type":"journal-article","created":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T15:02:06Z","timestamp":1716390126000},"page":"4651-4672","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["M-RRFS: A Memory-Based Robust Region Feature Synthesizer for Zero-Shot Object Detection"],"prefix":"10.1007","volume":"132","author":[{"given":"Peiliang","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8369-8886","authenticated-orcid":false,"given":"Dingwen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"De","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longfei","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,22]]},"reference":[{"key":"2112_CR1","doi-asserted-by":"crossref","unstructured":"Akata, Z., Perronnin, F., Harchaoui, Z., & Schmid, C. (2013). Label-embedding for attribute-based classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 819\u2013826","DOI":"10.1109\/CVPR.2013.111"},{"key":"2112_CR2","doi-asserted-by":"crossref","unstructured":"Akata, Z., Reed, S., Walter, D., Lee, H., & Schiele, B. (2015). Evaluation of output embeddings for fine-grained image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2927\u20132936","DOI":"10.1109\/CVPR.2015.7298911"},{"issue":"11s","key":"2112_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3519022","volume":"54","author":"S Antonelli","year":"2022","unstructured":"Antonelli, S., Avola, D., Cinque, L., Crisostomi, D., Foresti, G. L., Galasso, F., Marini, M. R., Mecca, A., & Pannone, D. (2022). Few-shot object detection: A survey. ACM Computing Surveys (CSUR), 54(11s), 1\u201337.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2112_CR4","unstructured":"Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. In: International conference on machine learning, PMLR, pp 214\u2013223"},{"key":"2112_CR5","doi-asserted-by":"crossref","unstructured":"Bansal, A., Sikka, K., Sharma, G., Chellappa, R., & Divakaran, A. (2018). Zero-shot object detection, in proceedings of the European Conference on Computer Vision (ECCV), pp 384\u2013400","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"2112_CR6","doi-asserted-by":"crossref","unstructured":"Bucher, M., Herbin, S., & Jurie, F. (2016). Improving semantic embedding consistency by metric learning for zero-shot classiffication. In: European conference on computer vision, Springer, pp 730\u2013746","DOI":"10.1007\/978-3-319-46454-1_44"},{"key":"2112_CR7","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers, in European conference on computer vision, Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2112_CR8","doi-asserted-by":"crossref","unstructured":"Chen, C., Han, J., & Debattista, K. (2024). Virtual category learning: A semi-supervised learning method for dense prediction with extremely limited labels. IEEE transactions on pattern analysis and machine intelligence","DOI":"10.1109\/TPAMI.2024.3367416"},{"key":"2112_CR9","doi-asserted-by":"crossref","unstructured":"Chen, S., Wang, W., Xia, B., Peng, Q., You, X., Zheng, F., & Shao, L. (2021). Free: Feature refinement for generalized zero-shot learning, in proceedings of the IEEE\/CVF international conference on computer vision, pp 122\u2013131","DOI":"10.1109\/ICCV48922.2021.00019"},{"key":"2112_CR10","doi-asserted-by":"crossref","unstructured":"Chen, S., Hong, Z., Xie, G.S., Yang, W., Peng, Q., Wang, K., Zhaom J., & You, X. (2022). Msdn: Mutually semantic distillation network for zero-shot learning, in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7612\u20137621","DOI":"10.1109\/CVPR52688.2022.00746"},{"key":"2112_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109270","volume":"137","author":"D Cheng","year":"2023","unstructured":"Cheng, D., Wang, G., Wang, B., Zhang, Q., Han, J., & Zhang, D. (2023). Hybrid routing transformer for zero-shot learning. Pattern Recognition, 137, 109270.","journal-title":"Pattern Recognition"},{"key":"2112_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, D., Wang, G., Wang, N., Zhang, D., Zhang, Q., & Gao, X. (2023). Discriminative and robust attribute alignment for zero-shot learning. IEEE Transactions on Circuits and Systems for Video Technology","DOI":"10.1109\/TCSVT.2023.3243205"},{"key":"2112_CR13","doi-asserted-by":"crossref","unstructured":"Christensen, A., Mancini, M., Koepke, A., Winther, O., & Akata, Z. (2023). Image-free classifier injection for zero-shot classification, in proceedings of the IEEE\/CVF international conference on computer vision, pp 19072\u201319081","DOI":"10.1109\/ICCV51070.2023.01748"},{"key":"2112_CR14","doi-asserted-by":"crossref","unstructured":"Dai, X., Wang, C., Li, H., Lin, S., Dong, L., Wu, J., & Wang, J. (2023). Synthetic feature assessment for zero-shot object detection, in 2023 IEEE international conference on multimedia and expo (ICME), IEEE, pp 444\u2013449","DOI":"10.1109\/ICME55011.2023.00083"},{"key":"2112_CR15","unstructured":"Demirel, B., Cinbis, R.G., & Ikizler-Cinbis, N. (2018). Zero-shot object detection by hybrid region embedding. arXiv preprint arXiv:1805.06157"},{"key":"2112_CR16","doi-asserted-by":"crossref","unstructured":"Demirel, B., Baran, O.B., & Cinbis, R.G. (2023). Meta-tuning loss functions and data augmentation for few-shot object detection, In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7339\u20137349","DOI":"10.1109\/CVPR52729.2023.00709"},{"key":"2112_CR17","unstructured":"Devlin, J., Chang, M.W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"issue":"12","key":"2112_CR18","doi-asserted-by":"publisher","first-page":"2861","DOI":"10.1109\/TPAMI.2018.2867870","volume":"41","author":"Z Ding","year":"2018","unstructured":"Ding, Z., Shao, M., & Fu, Y. (2018). Generative zero-shot learning via low-rank embedded semantic dictionary. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(12), 2861\u20132874.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2112_CR19","doi-asserted-by":"crossref","unstructured":"Elhoseiny, M., Zhu, Y., Zhang, H., & Elgammal, A. (2017). Link the head to the\" beak\": Zero shot learning from noisy text description at part precision, in proceedings of the IEEE conference on computer vision and pattern recognition, pp 5640\u20135649","DOI":"10.1109\/CVPR.2017.666"},{"issue":"2","key":"2112_CR20","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"issue":"8","key":"2112_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-021-3384-y","volume":"65","author":"C Fang","year":"2022","unstructured":"Fang, C., Tian, H., Zhang, D., Zhang, Q., Han, J., & Han, J. (2022). Densely nested top-down flows for salient object detection. Science China Information Sciences, 65(8), 1\u201314.","journal-title":"Science China Information Sciences"},{"key":"2112_CR22","doi-asserted-by":"crossref","unstructured":"Felix, R., Reid, I., Carneiro, G., et\u00a0al. (2018). Multi-modal cycle-consistent generalized zero-shot learning, In proceedings of the european conference on computer vision (ECCV), pp 21\u201337","DOI":"10.1007\/978-3-030-01231-1_2"},{"key":"2112_CR23","doi-asserted-by":"crossref","unstructured":"Feng, Y., Huang, X., Yang, P., Yu, J., & Sang, J. (2022). Non-generative generalized zero-shot learning via task-correlated disentanglement and controllable samples synthesis, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9346\u20139355","DOI":"10.1109\/CVPR52688.2022.00913"},{"key":"2112_CR24","doi-asserted-by":"crossref","unstructured":"Fu, Y., Hospedales, T.M., Xiang, T., Fu, Z., & Gong, S. (2014). Transductive multi-view embedding for zero-shot recognition and annotation, In European conference on computer vision, Springer, pp 584\u2013599","DOI":"10.1007\/978-3-319-10605-2_38"},{"issue":"12","key":"2112_CR25","doi-asserted-by":"publisher","first-page":"3136","DOI":"10.1109\/TPAMI.2019.2922175","volume":"42","author":"Y Fu","year":"2019","unstructured":"Fu, Y., Wang, X., Dong, H., Jiang, Y. G., Wang, M., Xue, X., & Sigal, L. (2019). Vocabulary-informed zero-shot and open-set learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(12), 3136\u20133152.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2112_CR26","doi-asserted-by":"crossref","unstructured":"Fu, Z., Xiang, T., Kodirov, E., & Gong, S. (2015). Zero-shot object recognition by semantic manifold distance, in, proceedings of the IEEE conference on computer vision and pattern recognition, pp 2635\u20132644","DOI":"10.1109\/CVPR.2015.7298879"},{"issue":"8","key":"2112_CR27","doi-asserted-by":"publisher","first-page":"2009","DOI":"10.1109\/TPAMI.2017.2737007","volume":"40","author":"Z Fu","year":"2017","unstructured":"Fu, Z., Xiang, T., Kodirov, E., & Gong, S. (2017). Zero-shot learning on semantic class prototype graph. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(8), 2009\u20132022.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"10","key":"2112_CR28","doi-asserted-by":"publisher","first-page":"3476","DOI":"10.1109\/TPAMI.2020.2985708","volume":"43","author":"J Gao","year":"2020","unstructured":"Gao, J., Zhang, T., & Xu, C. (2020). Learning to model relationships for zero-shot video classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10), 3476\u20133491.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2112_CR29","first-page":"17","volume":"30","author":"I Gulrajani","year":"2017","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. C. (2017). Improved training of Wasserstein Gans. Advances in Neural Information Processing Systems, 30, 17.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2112_CR30","doi-asserted-by":"crossref","unstructured":"Gupta, D., Anantharaman, A., Mamgain, N., Balasubramanian, V.N., Jawahar, C., et\u00a0al. (2020). A multi-space approach to zero-shot object detection, in proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1209\u20131217","DOI":"10.1109\/WACV45572.2020.9093384"},{"issue":"1","key":"2112_CR31","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/MSP.2017.2749125","volume":"35","author":"J Han","year":"2018","unstructured":"Han, J., Zhang, D., Cheng, G., Liu, N., & Xu, D. (2018). Advanced deep-learning techniques for salient and category-specific object detection: a survey. IEEE Signal Processing Magazine, 35(1), 84\u2013100.","journal-title":"IEEE Signal Processing Magazine"},{"key":"2112_CR32","doi-asserted-by":"crossref","unstructured":"Han, J., Ren, Y., Ding, J., Pan, X., Yan, K., & Xia, G.S. (2022). Expanding low-density latent regions for open-set object detection, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9591\u20139600","DOI":"10.1109\/CVPR52688.2022.00937"},{"key":"2112_CR33","doi-asserted-by":"crossref","unstructured":"Han, Z., Fu, Z., & Yang, J. (2020). Learning the redundancy-free features for generalized zero-shot object recognition, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12865\u201312874","DOI":"10.1109\/CVPR42600.2020.01288"},{"key":"2112_CR34","doi-asserted-by":"crossref","unstructured":"Han, Z., Fu, Z., Chen, S., & Yang, J. (2021). Contrastive embedding for generalized zero-shot learning, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2371\u20132381","DOI":"10.1109\/CVPR46437.2021.00240"},{"key":"2112_CR35","doi-asserted-by":"crossref","unstructured":"Hao, F., He, F., Liu, L., Wu, F., Tao, D., & Cheng, J. (2023). Class-aware patch embedding adaptation for few-shot image classification, in proceedings of the IEEE\/CVF international conference on computer vision, pp 18905\u201318915","DOI":"10.1109\/ICCV51070.2023.01733"},{"key":"2112_CR36","doi-asserted-by":"crossref","unstructured":"Hayat, N., Hayat, M., Rahman, S., Khan, S., Zamir, S.W., & Khan, F.S. (2020). Synthesizing the unseen for zero-shot object detection, in proceedings of the Asian conference on computer vision","DOI":"10.1007\/978-3-030-69535-4_10"},{"key":"2112_CR37","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9729\u20139738","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2112_CR38","doi-asserted-by":"crossref","unstructured":"Huang, H., Wang, C., Yu, P.S., & Wang, C.D. (2019). Generative dual adversarial network for generalized zero-shot learning, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 801\u2013810","DOI":"10.1109\/CVPR.2019.00089"},{"issue":"2","key":"2112_CR39","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1109\/JAS.2021.1004210","volume":"9","author":"P Huang","year":"2021","unstructured":"Huang, P., Han, J., Liu, N., Ren, J., & Zhang, D. (2021). Scribble-supervised video object segmentation. IEEE\/CAA Journal of Automatica Sinica, 9(2), 339\u2013353.","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"2112_CR40","doi-asserted-by":"crossref","unstructured":"Huang, P., Han, J., Cheng, D., & Zhang, D. (2022). Robust region feature synthesizer for zero-shot object detection, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7622\u20137631","DOI":"10.1109\/CVPR52688.2022.00747"},{"key":"2112_CR41","unstructured":"Jocher, G., Stoken, A., Borovec, J., Chaurasia, A., Changyu, L., Laughing, V., Hogan, A., Hajek, J., Diaconu, L., Kwon, Y., et\u00a0al. (2021). ultralytics\/yolov5: v5. 0-yolov5-p6 1280 models, aws, supervise. ly and youtube integrations. Version v5 0 Apr"},{"key":"2112_CR42","unstructured":"Kingma, D.P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114"},{"key":"2112_CR43","doi-asserted-by":"crossref","unstructured":"Kodirov, E., Xiang, T., & Gong, S. (2017). Semantic autoencoder for zero-shot learning, in proceedings of the IEEE conference on computer vision and pattern recognition, pp 3174\u20133183","DOI":"10.1109\/CVPR.2017.473"},{"key":"2112_CR44","doi-asserted-by":"crossref","unstructured":"Kong, X., Gao, Z., Li, X., Hong, M., Liu, J., Wang, C., Xie, Y., & Qu, Y. (2022). En-compactness: Self-distillation embedding & contrastive generation for generalized zero-shot learning, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9306\u20139315","DOI":"10.1109\/CVPR52688.2022.00909"},{"key":"2112_CR45","doi-asserted-by":"crossref","unstructured":"Kuo, C.W., Ma, C.Y., Huang, J.B., & Kira, Z. (2020). Featmatch: Feature-based augmentation for semi-supervised learning, In European conference on computer vision, Springer, pp 479\u2013495","DOI":"10.1007\/978-3-030-58523-5_28"},{"key":"2112_CR46","unstructured":"Kwon, G., & Al\u00a0Regib, G. (2022). A gating model for bias calibration in generalized zero-shot learning. IEEE Transactions on Image Processing"},{"key":"2112_CR47","doi-asserted-by":"crossref","unstructured":"Li, H., Mei, J., Zhou, J., & Hu, Y. (2023). Zero-shot object detection based on dynamic semantic vectors, in 2023 IEEE international conference on robotics and automation (ICRA), IEEE, pp 9267\u20139273","DOI":"10.1109\/ICRA48891.2023.10160870"},{"key":"2112_CR48","doi-asserted-by":"publisher","first-page":"8690","DOI":"10.1609\/aaai.v33i01.33018690","volume":"33","author":"Z Li","year":"2019","unstructured":"Li, Z., Yao, L., Zhang, X., Wang, X., Kanhere, S., & Zhang, H. (2019). Zero-shot object detection with textual descriptions. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 8690\u20138697.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2112_CR49","doi-asserted-by":"crossref","unstructured":"Liang, C., Ma, F., Zhu, L., Deng, Y., & Yang, Y. (2024). Caphuman: Capture your moments in parallel universes. arXiv preprint arXiv:2402.00627","DOI":"10.1109\/CVPR52733.2024.00612"},{"key":"2112_CR50","doi-asserted-by":"crossref","unstructured":"Liang, J., Hu, D., & Feng, J. (2021). Domain adaptation with auxiliary target domain-oriented classifier, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16632\u201316642","DOI":"10.1109\/CVPR46437.2021.01636"},{"key":"2112_CR51","doi-asserted-by":"crossref","unstructured":"Liao, W., Hu, K., Yang, M.Y., & Rosenhahn, B. (2022). Text to image generation with semantic-spatial aware gan. in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 18187\u201318196","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"2112_CR52","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.L. (2014). Microsoft coco: Common objects in context, in European conference on computer vision, Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2112_CR53","doi-asserted-by":"crossref","unstructured":"Liu, H., Zhang, L., Guan, J., & Zhou, S. (2023). Zero-shot object detection by semantics-aware detr with adaptive contrastive loss, in proceedings of the 31st ACM international conference on multimedia, pp 4421\u20134430","DOI":"10.1145\/3581783.3612523"},{"key":"2112_CR54","doi-asserted-by":"crossref","unstructured":"Liu, J., Sun, Y., Zhu, F., Pei, H., Yang, Y., & Li, W. (2022). Learning memory-augmented unidirectional metrics for cross-modality person re-identification, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 19366\u201319375","DOI":"10.1109\/CVPR52688.2022.01876"},{"key":"2112_CR55","doi-asserted-by":"crossref","unstructured":"Liu, N., Nan, K., Zhao, W., Liu, Y., Yao, X., Khan, S., Cholakkal, H., Anwer, R.M., Han, J,. & Khan, F.S. (2023). Multi-grained temporal prototype learning for few-shot video object segmentation, In proceedings of the IEEE\/CVF international conference on computer vision, pp 18862\u201318871","DOI":"10.1109\/ICCV51070.2023.01729"},{"key":"2112_CR56","doi-asserted-by":"crossref","unstructured":"Liu, R., Ge, Y., Choi, C.L., Wang, X., & Li, H. (2021). Divco: Diverse conditional image synthesis via contrastive generative adversarial network, In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16377\u201316386","DOI":"10.1109\/CVPR46437.2021.01611"},{"key":"2112_CR57","unstructured":"Liu, Y., Dang, Y., Gao, X., Han, J., & Shao, L. (2022). Zero-shot learning with attentive region embedding and enhanced semantics. IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2112_CR58","first-page":"38020","volume":"35","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Liu, N., Yao, X., & Han, J. (2022). Intermediate prototype mining transformer for few-shot semantic segmentation. Advances in Neural Information Processing Systems, 35, 38020\u201338031.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2112_CR59","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110452","volume":"152","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Dang, Y., Gao, X., Han, J., & Shao, L. (2024). Zero-shot sketch-based image retrieval via adaptive relation-aware metric learning. Pattern Recognition, 152, 110452.","journal-title":"Pattern Recognition"},{"key":"2112_CR60","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows, in proceedings of the IEEE\/CVF international conference on computer vision, pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2112_CR61","first-page":"3","volume":"30","author":"AL Maas","year":"2013","unstructured":"Maas, A. L., Hannun, A. Y., Ng, A. Y., et al. (2013). Rectifier nonlinearities improve neural network acoustic models. Citeseer, 30, 3.","journal-title":"Citeseer"},{"issue":"11","key":"2112_CR62","first-page":"18","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-sne. Journal of Machine Learning Research, 9(11), 18.","journal-title":"Journal of Machine Learning Research"},{"key":"2112_CR63","doi-asserted-by":"crossref","unstructured":"Mao, Q., Lee, H.Y., Tseng, H.Y., Ma, S., & Yang, M.H. (2019). Mode seeking generative adversarial networks for diverse image synthesis, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1429\u20131437","DOI":"10.1109\/CVPR.2019.00152"},{"key":"2112_CR64","first-page":"13","volume":"26","author":"T Mikolov","year":"2013","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Advances in Neural Information Processing Systems, 26, 13.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2112_CR65","unstructured":"Mikolov, T., Grave, E., Bojanowski, P., Puhrsch, C., & Joulin, A. (2018). Advances in pre-training distributed word representations. In: LREC"},{"key":"2112_CR66","doi-asserted-by":"crossref","unstructured":"Nie, H., Wang, R., & Chen, X. (2022). From node to graph: Joint reasoning on visual-semantic relational graph for zero-shot detection, in proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1109\u20131118","DOI":"10.1109\/WACV51458.2022.00171"},{"key":"2112_CR67","doi-asserted-by":"crossref","unstructured":"Pambala, A., Dutta, T., & Biswas, S. (2020). Generative model with semantic embedding and integrated classifier for generalized zero-shot learning, in proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 1237\u20131246","DOI":"10.1109\/WACV45572.2020.9093625"},{"issue":"5","key":"2112_CR68","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s11263-022-01590-z","volume":"130","author":"J Pan","year":"2022","unstructured":"Pan, J., Zhu, P., Zhang, K., Cao, B., Wang, Y., Zhang, D., Han, J., & Hu, Q. (2022). Learning self-supervised low-rank network for single-stage weakly and semi-supervised semantic segmentation. International Journal of Computer Vision, 130(5), 1181\u20131195.","journal-title":"International Journal of Computer Vision"},{"issue":"4","key":"2112_CR69","first-page":"4051","volume":"45","author":"F Pourpanah","year":"2023","unstructured":"Pourpanah, F., Abdar, M., Luo, Y., Zhou, X., Wang, R., Lim, C. P., Wang, X. Z., & Wu, Q. J. (2023). A review of generalized zero-shot learning methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4), 4051\u20134070.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2112_CR70","unstructured":"Rahman, S., Khan, S., & Barnes, N. (2018). Polarity loss for zero-shot object detection. arXiv preprint arXiv:1811.08982"},{"key":"2112_CR71","doi-asserted-by":"crossref","unstructured":"Rahman, S., Khan, S., & Porikli, F. (2018). Zero-shot object detection: Learning to simultaneously recognize and localize novel concepts, in Asian conference on computer vision, Springer, pp 547\u2013563","DOI":"10.1007\/978-3-030-20887-5_34"},{"issue":"6","key":"2112_CR72","first-page":"1137","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 39(6), 1137\u20131149.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"6","key":"2112_CR73","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2016). Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137\u20131149.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2112_CR74","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115, 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"2112_CR75","first-page":"16","volume":"29","author":"T Salimans","year":"2016","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016). Improved techniques for training gans. Advances in Neural Information Processing Systems, 29, 16.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2112_CR76","unstructured":"Sarma, S., KUMAR, S., & Sur, A. (2022). Resolving semantic confusions for improved zero-shot detection. In: 33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022, BMVA Press"},{"key":"2112_CR77","doi-asserted-by":"crossref","unstructured":"Schonfeld, E., Ebrahimi, S., Sinha, S., Darrell, T., & Akata, Z. (2019). Generalized zero-and few-shot learning via aligned variational autoencoders, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8247\u20138255","DOI":"10.1109\/CVPR.2019.00844"},{"key":"2112_CR78","first-page":"2015","volume":"28","author":"K Sohn","year":"2015","unstructured":"Sohn, K., Lee, H., & Yan, X. (2015). Learning structured output representation using deep conditional generative models. Advances in Neural Information Processing Systems, 28, 2015.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2112_CR79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3582688","volume":"55","author":"Y Song","year":"2023","unstructured":"Song, Y., Wang, T., Cai, P., Mondal, S. K., & Sahoo, J. P. (2023). A comprehensive survey of few-shot learning: Evolution, applications, challenges, and opportunities. ACM Computing Surveys, 55, 1\u201340.","journal-title":"ACM Computing Surveys"},{"key":"2112_CR80","doi-asserted-by":"crossref","unstructured":"Su, H., Li, J., Chen, Z., Zhu, L., & Lu, K. (2022). Distinguishing unseen from seen for generalized zero-shot learning, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7885\u20137894","DOI":"10.1109\/CVPR52688.2022.00773"},{"key":"2112_CR81","first-page":"15","volume":"28","author":"S Sukhbaatar","year":"2015","unstructured":"Sukhbaatar, S., Weston, J., Fergus, R., et al. (2015). End-to-end memory networks. Advances in Neural Information Processing Systems, 28, 15.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2112_CR82","doi-asserted-by":"crossref","unstructured":"Suo, Y., Zhu, L., & Yang, Y. (2023). Text augmented spatial-aware zero-shot referring image segmentation. arXiv preprint arXiv:2310.18049","DOI":"10.18653\/v1\/2023.findings-emnlp.73"},{"key":"2112_CR83","doi-asserted-by":"crossref","unstructured":"Trosten, D.J., Chakraborty, R., L\u00f8kse, S., Wickstr\u00f8m, K.K., & Jenssen, R., Kampffmeyer, M.C. (2023). Hubs and hyperspheres: Reducing hubness and improving transductive few-shot learning with hyperspherical embeddings, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7527\u20137536","DOI":"10.1109\/CVPR52729.2023.00727"},{"key":"2112_CR84","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., & Liao, H.Y.M. (2023). Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"issue":"5","key":"2112_CR85","first-page":"5549","volume":"45","author":"X Wang","year":"2022","unstructured":"Wang, X., & Qi, G. J. (2022). Contrastive learning with stronger augmentations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5), 5549\u20135560.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2112_CR86","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, H., Huang, W., Scott, M.R. (2020). Cross-batch memory for embedding learning, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6388\u20136397","DOI":"10.1109\/CVPR42600.2020.00642"},{"key":"2112_CR87","doi-asserted-by":"crossref","unstructured":"Wang, Z., Hao, Y., Mu, T., Li, O., Wang, S., & He, X. (2023). Bi-directional distribution alignment for transductive zero-shot learning, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 19893\u201319902","DOI":"10.1109\/CVPR52729.2023.01905"},{"key":"2112_CR88","doi-asserted-by":"crossref","unstructured":"Wu, J., Zhang, T., Zha, Z.J., Luo, J., Zhang, Y., & Wu, F. (2020). Self-supervised domain-aware generative network for generalized zero-shot learning, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12767\u201312776","DOI":"10.1109\/CVPR42600.2020.01278"},{"key":"2112_CR89","doi-asserted-by":"crossref","unstructured":"Xian, Y., Akata, Z., Sharma, G., Nguyen, Q., Hein, M., & Schiele, B. (2016). Latent embeddings for zero-shot classification, in proceedings of the IEEE conference on computer vision and pattern recognition, pp 69\u201377","DOI":"10.1109\/CVPR.2016.15"},{"key":"2112_CR90","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lorenz, T., Schiele, B., & Akata, Z. (2018). Feature generating networks for zero-shot learning. in proceedings of the IEEE conference on computer vision and pattern recognition, pp 5542\u20135551","DOI":"10.1109\/CVPR.2018.00581"},{"key":"2112_CR91","unstructured":"Xu, B., Zeng, Z., Lian, C., & Ding, Z. (2022). Generative mixup networks for zero-shot learning. IEEE transactions on neural networks and learning systems"},{"key":"2112_CR92","doi-asserted-by":"crossref","unstructured":"Xu, J., & Le, H. (2022). Generating representative samples for few-shot classification, in proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9003\u20139013","DOI":"10.1109\/CVPR52688.2022.00880"},{"key":"2112_CR93","unstructured":"Yan, C., Chang, X., Luo, M., Liu, H., Zhang, X., & Zheng, Q. (2022). Semantics-guided contrastive network for zero-shot object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2112_CR94","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.neunet.2023.12.006","volume":"171","author":"J Yao","year":"2024","unstructured":"Yao, J., Han, L., Guo, G., Zheng, Z., Cong, R., Huang, X., Ding, J., Yang, K., Zhang, D., & Han, J. (2024). Position-based anchor optimization for point supervised dense nuclei detection. Neural Networks, 171, 159\u2013170.","journal-title":"Neural Networks"},{"issue":"6","key":"2112_CR95","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.3046647","volume":"44","author":"D Zhang","year":"2020","unstructured":"Zhang, D., Zeng, W., Yao, J., & Han, J. (2020). Weakly supervised object detection using proposal-and semantic-level relationships. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(6), 3349.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"9","key":"2112_CR96","first-page":"5866","volume":"44","author":"D Zhang","year":"2021","unstructured":"Zhang, D., Han, J., Cheng, G., & Yang, M. H. (2021). Weakly supervised object localization and detection: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9), 5866\u20135885.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2112_CR97","unstructured":"Zhang, D., Guo, G., Zeng, W., Li, L., & Han, J. (2022). Generalized weakly supervised object localization. IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2112_CR98","doi-asserted-by":"crossref","unstructured":"Zhang, D., Li, H., Zeng, W., Fang, C., Cheng, L., Cheng, M.M., & Han, J. (2023). Weakly supervised semantic segmentation via alternate self-dual teaching. IEEE Transactions on Image Processing","DOI":"10.1109\/TIP.2023.3343112"},{"issue":"8","key":"2112_CR99","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","volume":"41","author":"H Zhang","year":"2018","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., & Metaxas, D. N. (2018). Stackgan++: Realistic image synthesis with stacked generative adversarial networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(8), 1947\u20131962.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2112_CR100","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xiang, T., & Gong, S. (2017). Learning a deep embedding model for zero-shot learning, in: proceedings of the IEEE conference on computer vision and pattern recognition, pp 2021\u20132030","DOI":"10.1109\/CVPR.2017.321"},{"key":"2112_CR101","doi-asserted-by":"crossref","unstructured":"Zhang, L., Wang, X., Yao, L., Wu, L., & Zheng, F. (2020). Zero-shot object detection via learning an embedding from semantic space to visual space. In: Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence $$\\{$$IJCAI-PRICAI-20$$\\}$$, International Joint Conferences on Artificial Intelligence Organization","DOI":"10.24963\/ijcai.2020\/126"},{"key":"2112_CR102","doi-asserted-by":"crossref","unstructured":"Zhang, W., Janson, P., Yi, K., Skorokhodov, I., & Elhoseiny, M. (2023). Continual zero-shot learning through semantically guided generative random walks, in proceedings of the IEEE\/CVF international conference on computer vision, pp 11574\u201311585","DOI":"10.1109\/ICCV51070.2023.01063"},{"key":"2112_CR103","doi-asserted-by":"crossref","unstructured":"Zhang, X., Liu, Y., Dang, Y., Gao, X., Han, J., & Shao, L. (2024). Adaptive relation-aware network for zero-shot classification. Neural Networks, 174, 106227.","DOI":"10.1016\/j.neunet.2024.106227"},{"key":"2112_CR104","doi-asserted-by":"crossref","unstructured":"Zhao, S., Gao, C., Shao, Y., Li, L., Yu, C., Ji, Z., & Sang, N. (2020). Gtnet: Generative transfer network for zero-shot object detection. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 12967\u201312974.","DOI":"10.1609\/aaai.v34i07.6996"},{"key":"2112_CR105","doi-asserted-by":"publisher","first-page":"3454","DOI":"10.1609\/aaai.v36i3.20256","volume":"36","author":"X Zhao","year":"2022","unstructured":"Zhao, X., Shen, Y., Wang, S., & Zhang, H. (2022). Boosting generative zero-shot learning by synthesizing diverse features with attribute augmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 36, 3454\u20133462.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2112_CR106","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Huang, R., Han, C., Huang, X., & Cui, L. (2020). Background learnable cascade for zero-shot object detection, in proceedings of the asian conference on computer vision","DOI":"10.1007\/978-3-030-69535-4_7"},{"key":"2112_CR107","doi-asserted-by":"crossref","unstructured":"Zhu, P., Wang, H., & Saligrama, V. (2020). Don\u2019t even look once: Synthesizing features for zero-shot detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11693\u201311702","DOI":"10.1109\/CVPR42600.2020.01171"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02112-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02112-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02112-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T18:33:01Z","timestamp":1732041181000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02112-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,22]]},"references-count":107,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["2112"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02112-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,22]]},"assertion":[{"value":"21 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}